GPU model | GF108 | GK20A |
---|---|---|
GPU variant | GF108-400-A1 | — |
Architecture | Fermi | Kepler 2.0 |
Foundry | TSMC | TSMC |
Manufacturing process | 40 nm | 28 nm |
Number of transistors | 585 million | unknown |
Die size | 116 mm² | unknown |
Release date | Feb 9th, 2011 | — |
---|---|---|
Generation | GeForce 400 | — |
Production | End-of-life | — |
Interface | PCIe 1.0 x16 | — |
Reviews | 5 in our database | — |
Predecessor | GeForce 200 | — |
Successor | GeForce 500 | — |
GPU clock | 810 MHz | — |
---|---|---|
Shader clock | 1620 MHz | — |
Memory clock | 667 MHz 1334 Mbps effective | System Shared |
Base clock | — | 756 MHz |
Boost clock | — | 951 MHz |
Memory size | 1024 MB | System Shared |
---|---|---|
Memory type | DDR3 | System Shared |
Memory bus width | 128 bit | System Shared |
Bandwidth | 21.34 GB/s | System Dependent |
Shading units | 96 | 192 |
---|---|---|
TMUs | 16 | 8 |
ROPs | 4 | 4 |
SM count | 2 | — |
Cache L1 | 64 KB (per SM) | 16 KB (per SMX) |
Cache L2 | 256 KB | 128 KB |
SMX count | — | 1 |
Pixel rate | 3.240 GPixel/s | 3.804 GPixel/s |
---|---|---|
Texture rate | 12.96 GTexel/s | 7.608 GTexel/s |
FP32 (float) performance | 311.0 GFLOPS | 365.2 GFLOPS |
FP64 (double) performance | 25.92 GFLOPS (1:12) | 11.41 GFLOPS (1:32) |
Slot width | Single-slot | IGP |
---|---|---|
Length | 145 mm 5.7 inches | — |
TDP | 65 W | 8 W |
Suggested PSU | 250 W | — |
Outputs | 1x DVI1x HDMI1x VGA | No outputs |
Power connectors | None | — |
Board number | P1071 | — |
DirectX | 12 (11_0) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | ES 3.1 |
OpenCL | 1.1 | — |
Vulkan | — | 1.1 |
CUDA | 2.1 | 3.2 |
Shader model | 5.1 | 5.1 |
Release date | — | Oct 15th, 2014 |
---|---|---|
Generation | — | Tegra |
Production | — | End-of-life |
Interface | — | IGP |